© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 9046
    Prev
    Next
    INDEX
    Explanations

    references to prestigious educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    üzel
    -0.16
    èĵ
    -0.16
    enza
    -0.15
    irut
    -0.15
    ipar
    -0.15
    steen
    -0.14
    tach
    -0.14
    ookeeper
    -0.14
    lander
    -0.14
     Gael
    -0.14
    POSITIVE LOGITS
     Oxford
    0.32
     Cambridge
    0.30
     Ox
    0.26
     Bras
    0.24
     college
    0.22
     Gon
    0.22
     Tutorial
    0.22
     Rhodes
    0.21
     colleges
    0.21
     prep
    0.20
    Activations Density 0.019%

    No Known Activations